© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 191
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    File paths or extensions

    np_acts-logits-general · gemini-2.0-flash

    . and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stino
    -0.54
    uurs
    -0.48
     فريبيس
    -0.47
    "
    -0.46
     perek
    -0.46
     stesso
    -0.45
    diğim
    -0.45
     ob
    -0.45
     SwitchCompat
    -0.45
    .
    -0.44
    POSITIVE LOGITS
    fromnode
    0.87
     `.
    0.80
    ','.
    0.79
     resourceCulture
    0.74
    ">.
    0.73
    Hozzáférés
    0.73
     /\.
    0.73
    (".
    0.71
    存于互联网档案馆
    0.69
     <.
    0.68
    Activations Density 0.212%

    No Known Activations